Commit Graph

58 Commits

Author SHA1 Message Date
xiaoju 7db43005de fix(cli): align workflow list with thread start via parent traversal
CI / check (pull_request) Successful in 3m12s
discoverProjectWorkflows() now searches .workflow/ in ancestor directories,
matching findWorkflowInParents() behavior used by `uwf thread start`. Also
documents project-local .workflow/ auto-discovery in usage, cli, and
workflow-authoring references.

Fixes #162
2026-06-07 15:08:36 +00:00
xiaoju ae757e4d44 feat(cli): thread list defaults to active threads only
CI / check (pull_request) Successful in 2m52s
Closes #147. Changes default behavior of `uwf thread list` to show only
active threads (idle + running). Adds `--all` flag to opt into the
previous full-list behavior. Explicit `--status` still wins over `--all`.

- cmdThreadList gains a `showAll: boolean` parameter (default false)
- CLI registers `--all` option and passes it through
- Test suite includes new `default behavior (issue #147)` describe block
  covering 9 scenarios; existing tests updated where they implicitly
  relied on the old "show everything" behavior
- README, cli-reference, and usage-reference updated to document the
  new default and the `--all` flag

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-06-07 13:46:25 +00:00
xiaoju 10113f6ec6 chore(cli): clean up step-ask nits from PR #156 review
CI / check (pull_request) Successful in 2m23s
- Remove dead-code detailRef null guards (already validated upstream)
- Fix ?: to explicit T | null on external error type boundary
- Drop unnecessary async from resolveAskWorkflow (no await)
- Simplify double negation: opts.fork !== false → opts.fork

Refs #146
2026-06-07 11:44:45 +00:00
xiaoju b5e094ab4d feat(cli): step ask — read-only query to historical step sessions
CI / check (pull_request) Successful in 2m46s
Adds `uwf step ask <step-hash> -p <prompt>` for asking follow-up
questions to a completed step's agent without mutating thread state.

- Fork-by-default: creates and caches a fork session per step (cache
  key `<stepHash>:ask`); subsequent asks reuse it.
- `--no-fork` fallback: spawns a fresh session with the step's detail
  ref injected as context.
- `--agent` overrides the recorded agent; otherwise resolves from the
  step's agent field via config alias.
- Updates `packages/cli/README.md` and `packages/util/src/usage-reference.ts`
  so the new subcommand is discoverable via README and `uwf prompt usage`.

Fixes #146
2026-06-07 10:33:41 +00:00
scottwei 4c5cc27d52 Merge pull request 'feat(cli): thread poke — re-run head step with supplementary prompt' (#148) from fix/144-thread-poke into main
CI / check (push) Successful in 2m44s
Reviewed-on: #148
Reviewed-by: xiaomo <xiaomooo@shazhou.work>
2026-06-07 07:53:27 +00:00
xingyue df244c52e8 Revert "Merge pull request 'chore: release — bump @ocas/* ^0.4.0, @shazhou/proman ^0.6.3' (#150) from release/bump-ocas-proman into main"
CI / check (pull_request) Successful in 3m45s
This reverts commit 9d0c6df62c, reversing
changes made to 00d960daba.
2026-06-07 15:25:31 +08:00
xiaoju e4c46c8150 feat(cli): add thread poke command
CI / check (pull_request) Successful in 3m43s
Re-runs the head step's agent with a supplementary prompt and replaces
the head step (rewires new step's prev to old head's prev) instead of
appending. Skips moderator re-route — the role of the head step is
reused.

Fixes #144
2026-06-07 07:19:26 +00:00
xingyue 0f5bb1f191 chore: release — bump @ocas/* ^0.4.0, @shazhou/proman ^0.6.3
CI / check (pull_request) Successful in 2m35s
Published:
- @united-workforce/protocol@0.1.1
- @united-workforce/util-agent@0.1.2
- @united-workforce/agent-builtin@0.1.3
- @united-workforce/agent-claude-code@0.1.4
- @united-workforce/agent-hermes@0.1.5
- @united-workforce/agent-mock@0.1.3
- @united-workforce/cli@0.3.1
- @united-workforce/eval@0.1.6
2026-06-07 15:06:43 +08:00
xingyue 3a26285872 chore: bump @ocas/* to ^0.4.0 and @shazhou/proman to ^0.6.3
CI / check (pull_request) Successful in 3m28s
2026-06-07 14:12:03 +08:00
xiaoju 513846f4ab fix: update solve-issue test path from .workflows/ to examples/
CI / check (pull_request) Successful in 1m52s
Tests were referencing the old .workflows/ directory which no longer exists.
Updated workflow path and aligned assertions with current procedure content.

小橘 🍊(NEKO Team)
2026-06-06 23:01:33 +00:00
xiaoju d97840cf8d chore: release cli@0.3.0 util@0.1.3 agent-hermes@0.1.3 agent-claude-code@0.1.2 agent-builtin@0.1.2 agent-mock@0.1.2
CI / check (push) Successful in 1m46s
2026-06-06 00:13:48 +00:00
xiaoju f989dee85b fix: bootstrap — remind to restart session after skill install/update
CI / check (pull_request) Successful in 1m42s
- Step 3 (fresh install): warn skills not active until new session
- Step 2 (upgrade): same reminder after regenerating skills
- Step 3 (upgrade): add v0.2.1 migration note for enum → const

Refs #123
2026-06-05 23:48:53 +00:00
xiaoju 68079cc003 fix: unify $status to const-only, drop enum support (#123)
CI / check (pull_request) Successful in 1m43s
- Validator: hasStatusConst/getConstStatuses replace enum checks
- enum in $status is now rejected with clear error message
- All docs/examples/tests migrated from enum to const/oneOf
- bootstrap hello.yaml updated

Fixes #123
2026-06-05 23:31:56 +00:00
xiaoju adc3982a4a fix: bootstrap agent discovery + adapter version independence (#120)
CI / check (pull_request) Successful in 1m42s
- Step 1: detect hermes/claude before choosing adapter
- Adapter versions independent from CLI — install @latest
- ACP verification: hermes acp --help
- Remove uwf-builtin (not ready)

Refs #120
2026-06-05 22:29:35 +00:00
xiaoju caba82fe36 fix: bootstrap PATH fix guidance — find binary location + update shell config (#118 #1)
CI / check (pull_request) Successful in 1m44s
2026-06-05 16:45:33 +00:00
xiaoju 6aee2ed5ef fix: bootstrap docs — pnpm/npm parity, adapter order, preset table (#118)
CI / check (pull_request) Successful in 2m27s
- Show pnpm and npm install commands side-by-side
- Clarify adapter must be installed before uwf setup --agent
- Add version verification steps with PATH troubleshooting
- --agent takes adapter command name (uwf-hermes), not npm package
- Preset providers shown as table with default base URLs
- Non-preset providers must specify --base-url manually

Fixes #118 (#2, #3, #4, #5)
2026-06-05 16:41:35 +00:00
xiaoju 7a788a9d90 fix: suppress ExperimentalWarning, PEP 668 guidance, setup help
CI / check (pull_request) Successful in 2m31s
- All 5 CLI bins: shebang --disable-warning=ExperimentalWarning
- Remove NODE_OPTIONS injection from thread.ts spawn (redundant now)
- Bootstrap pip install: venv (recommended) / pipx / source options
- setup --help mentions interactive wizard mode
- Update shebang test to accept -S flag

Fixes #116
2026-06-05 16:12:06 +00:00
xiaoju fde87b6274 fix: setup UX improvements — adapter check, ENOENT, SQLite warning, VERSION, PATH docs
CI / check (pull_request) Successful in 2m24s
- setup validates adapter binary availability, prints install command if missing
- setup prints 'Config saved to <path> ✓' on success
- spawn ENOENT gives actionable error with which command
- SQLite ExperimentalWarning suppressed via NODE_OPTIONS
- bootstrap VERSION reads cli package.json (was reading util)
- bootstrap PATH guidance is shell-agnostic

Fixes #114
2026-06-05 15:42:22 +00:00
xiaoju 3be92bfac2 fix: bootstrap adds Step 0 environment pre-flight check
CI / check (pull_request) Successful in 3m44s
- Node.js, pnpm/npm, global bin PATH, hermes CLI checks with FIX instructions
- Agent must pass all checks before proceeding to install
- Install commands changed from npm to pnpm (with npm fallback)
- hermes PATH guidance moved from Step 1 to Step 0

Fixes #112
2026-06-05 14:09:33 +00:00
xiaoju 5450bc1230 fix: workflow-authoring flat schema, bootstrap PATH guidance
CI / check (pull_request) Successful in 2m18s
- #110.3: flat schema example uses enum: [done] instead of bare const
  (bare const fails validate-semantic hasStatusEnum check)
- #110.4: bootstrap adds 'which hermes' PATH check and venv guidance
- #110.1: already fixed in rc.1 (inline hello.yaml)
- #110.2: already fixed in rc.1 (capabilities: [] present)

Fixes #110
2026-06-05 11:44:20 +00:00
xiaoju 57ae6d1755 fix: preset base-url auto-fill, bootstrap ACP docs, friendlier errors
CI / check (pull_request) Successful in 2m26s
- #106: uwf setup --provider <preset> now auto-fills --base-url
- #107: bootstrap documents hermes ACP dependency (pip install hermes-agent[acp])
- #107: verify step uses inline hello.yaml instead of missing examples/eval-simple.yaml
- #108: workflow name mismatch error suggests how to fix (rename file or change YAML name)

Fixes #106, Fixes #107, Fixes #108
2026-06-05 11:06:35 +00:00
xiaoju c5eb8b79d1 fix: expand bootstrap prompt with full onboarding and upgrade guide
CI / check (pull_request) Successful in 2m56s
- Fresh install: CLI + adapter install, uwf setup, skills, e2e verify
- Upgrade: update packages, regenerate skills, migrate workflows
- Explicitly tells agent to ask user for provider/api-key/model
- Lists all available adapters with install commands
- Documents v0.2.0 $START migration

Fixes #104
2026-06-05 10:35:01 +00:00
xiaoju 36a3ca6a08 chore: bump cli@0.2.0, util@0.1.2
CI / check (push) Successful in 2m25s
2026-06-05 10:11:19 +00:00
xiaoju fbfd31a042 feat: replace $START _ status with new/resume semantics
CI / check (pull_request) Successful in 2m27s
BREAKING: All workflow YAML files must update $START._ to $START.new + $START.resume.
The resume edge prompt replaces the previously hardcoded resume message.

- evaluate.ts: remove START_ROLE/START_STATUS special case, use $status like all nodes
- thread.ts: resolveEvaluateArgs passes 'new', cmdThreadResume passes 'resume'
- validate.ts: reject '_' everywhere (no longer valid)
- validate-semantic.ts: require 'new' and 'resume' edges on $START
- All workflow YAMLs and test fixtures updated

Fixes #101
2026-06-05 09:30:09 +00:00
xiaoju a536efee00 fix: simplify prompt subcommands, framework-agnostic bootstrap
CI / check (pull_request) Successful in 3m24s
- `uwf prompt usage` now outputs only the usage skill (was three combined)
- `uwf prompt bootstrap` replaces `setup` with framework-agnostic instructions
- Remove `usage-reference` and `setup` subcommands
- Remove `generateBootstrapReference` from util (moved to cli)

Fixes #99

小橘 🍊(NEKO Team)
2026-06-05 08:52:35 +00:00
xiaoju 427568a21d chore: version bump agent-hermes@0.1.1 cli@0.1.1 eval@0.1.2
CI / check (push) Successful in 2m37s
小橘 🍊(NEKO Team)
2026-06-05 06:29:25 +00:00
xiaoju 825f0c641a fix: resolve --agent override via config alias before raw command
CI / check (pull_request) Successful in 3m37s
When --agent is passed to uwf thread exec, try config.agents[alias]
first (e.g. 'hermes' → config.agents.hermes = {command: 'uwf-hermes'}),
then fall back to parseAgentOverride for raw command names.

Also change eval CLI default --agent from 'hermes' to 'uwf-hermes'
so it works without config alias lookup.

Refs #91
2026-06-05 04:20:09 +00:00
xiaoju c892b9125b chore: remove prepublishOnly guards (proman handles release)
CI / check (push) Successful in 2m26s
2026-06-05 02:29:53 +00:00
xiaoju 63cb4d3645 fix: remove _ single-exit for user roles
CI / check (pull_request) Successful in 3m7s
$START keeps _ (special entry node). All user-defined roles now require
explicit $status enum in frontmatter + matching graph keys.

- moderator: remove UNIT_STATUS fallback, error on missing $status
- validate: reject _ graph keys for non-$START roles
- validate-semantic: remove checkSingleExitRole(), require $status enum
- update all test fixtures to use explicit status values
- fix examples/analyze-topic.yaml

Fixes #86
2026-06-05 02:00:45 +00:00
xiaoju 248ac710fd feat: agent-mock emits fixed $usage stats
CI / check (pull_request) Successful in 1m41s
- Mock agent returns {turns:1, inputTokens:0, outputTokens:0, duration:0}
- E2E test 1 (linear workflow) asserts usage in CAS step nodes
- 747 tests pass

Fixes #75
Refs #68
2026-06-04 22:19:29 +00:00
xiaomo 172c232e61 Merge pull request 'feat: add $usage field to adapter protocol' (#80) from feat/74-usage-in-protocol into main
CI / check (push) Successful in 1m41s
feat: add $usage field to adapter protocol (#80)
2026-06-04 22:14:12 +00:00
xiaoju 99f40c2488 feat: add $usage field to adapter protocol
CI / check (pull_request) Successful in 2m28s
- Add Usage type to protocol (turns, inputTokens, outputTokens, duration)
- Add usage to StepRecord, StepNodePayload, StepEntry, STEP_NODE_SCHEMA
- Thread usage through util-agent extract pipeline (writeStepNode → persistStep → createAgent)
- All adapters return usage: null as placeholder (mock, hermes, claude-code, builtin)
- 746 tests pass, no breaking changes (usage not in schema required array)

Fixes #74
Refs #68
2026-06-04 15:41:07 +00:00
xingyue 83bcda60ff refactor(prompt): rename subcommands and add frontmatter output
CI / check (pull_request) Successful in 3m1s
- Rename: user→usage-reference, author→workflow-authoring, adapter→adapter-developing
- Remove: developer (content lives in CLAUDE.md)
- All prompts output complete SKILL.md with YAML frontmatter
- Setup instructions simplified: uwf prompt bootstrap > SKILL.md
- Remove all bun references, use pnpm/npm
- Fix CLAUDE.md: fixed→independent versioning
- Delete old reference files (user/author/developer/adapter)

Closes #66
2026-06-04 22:46:11 +08:00
xiaoju 3401873051 chore: rebranding cleanup — reset versions to 0.1.0, bun→pnpm in docs
CI / check (pull_request) Successful in 2m49s
- All 9 packages reset to version 0.1.0
- CLAUDE.md: bun→pnpm, fixed→independent versioning, proman commands
- docs/architecture.md: bun→pnpm in toolchain table
- docs/sync-readme.md: bun→pnpm in conventions
2026-06-04 13:05:26 +00:00
xiaoju 18170a4313 refactor: extract validateCount, replace CLI spawn with direct import
CI / check (pull_request) Successful in 2m24s
- Extract validateCount() from cmdThreadExec (throw instead of process.exit)
- 5 validation tests now import validateCount directly (no subprocess)
- Only --help tests still spawn CLI (need Commander output)
- Test time: 1.7s → 475ms

Fixes #61
2026-06-04 12:31:17 +00:00
xiaoju 66c2e2a79b fix: use node dist/cli.js instead of npx tsx in thread-step-count tests
CI / check (pull_request) Successful in 3m30s
npx tsx hangs in CI Docker (30s+ timeout). node dist/cli.js runs in <2s.
2026-06-04 11:57:32 +00:00
xiaoju 58b58d511e fix: add timeout to cmdThreadExec count logic tests
CI / check (pull_request) Failing after 4m17s
2026-06-04 11:48:46 +00:00
xiaoju 596c05bfcc fix: use node dist/cli.js instead of npx tsx in prompt help test
CI / check (pull_request) Failing after 3m40s
npx tsx fails in CI (tsx not found, npm tries to install it)
2026-06-04 11:32:09 +00:00
xiaoju d26f54e8ea fix: biome format + remove unused noConsole suppressions
CI / check (pull_request) Failing after 3m58s
2026-06-04 11:22:46 +00:00
xiaoju 883bd79bcb fix: add timeout to CI-slow tests + check stderr for help output
CI / check (pull_request) Failing after 1m55s
2026-06-04 11:18:49 +00:00
xiaoju 63454a4cfd fix: OCAS_DIR → OCAS_HOME in test helpers + exclude integration tests from CI
CI / check (pull_request) Failing after 2m27s
- Remaining OCAS_DIR references caused test isolation failures
- agent-hermes integration tests need 'hermes' CLI, skip in CI

Fixes #58
2026-06-04 11:06:42 +00:00
xiaoju 9f5891169e fix: add missing workflow destructure in current-role test
CI / check (pull_request) Failing after 1m37s
The createMarker call used shorthand 'workflow' but the variable
was not destructured from cmdThreadStart.

Fixes #56
2026-06-04 10:56:44 +00:00
xiaomo f56e24cf82 Merge pull request 'test: expand E2E coverage — suspend, count, mustache, completed resume' (#51) from test/33-more-e2e into main
CI / check (push) Failing after 1m28s
test: expand E2E coverage — suspend, count, mustache, completed resume (#51)
2026-06-04 09:04:09 +00:00
xiaoju 974c2b8f1b test: add E2E tests for suspend/resume, --count, mustache, and completed resume (#33)
CI / check (pull_request) Failing after 1m40s
4 new E2E scenarios:
4. $SUSPEND → resume lifecycle (suspendedRole/suspendMessage metadata)
5. --count 3 runs entire pipeline in one invocation
6. mustache template variables rendered into edgePrompt
7. completed thread resume (衔尾蛇: end → start, CAS chain preserved)

Total: 7 E2E scenarios, all passing.
2026-06-04 09:03:01 +00:00
xingyue dbb7885ffd chore: fix biome check errors (40 → 0)
CI / check (pull_request) Failing after 1m39s
- Auto-fix: import sorting, formatting (17 files)
- Unsafe auto-fix: unused vars, template literals (7 files)
- Manual: nursery/noConsole → suspicious/noConsole suppression
- Manual: suppress noExcessiveCognitiveComplexity for cmdThreadResume and parseWorkflowPayload
- Manual: remove unused destructured vars in current-role tests

Closes #48
2026-06-04 16:45:45 +08:00
xiaomo cd7e4e77ff Merge pull request 'feat: agent-mock package for deterministic E2E testing (#33)' (#44) from test/33-mock-agent into main
CI / check (push) Failing after 1m38s
feat: agent-mock package for deterministic E2E testing (#44)
2026-06-04 08:38:51 +00:00
xiaoju 80e8efb05e test: E2E integration tests with uwf-mock agent (#33)
CI / check (pull_request) Failing after 2m30s
Three scenarios testing the full CLI pipeline:
1. Linear workflow (planner → worker → $END): CAS chain integrity
2. Loop workflow (developer ↔ reviewer): moderator routing through cycles
3. Role mismatch detection: agent catches routing bugs

Uses workflow add → thread start → thread exec with uwf-mock,
verifying CAS state, thread lifecycle, and error handling.

Updated assertions to use getThread().status === 'completed'
(aligned with PR #45 unified thread storage).

Refs #33
2026-06-04 08:06:22 +00:00
xingyue 06af1dc668 fix: resolve workflow from CAS chain in collectCompletedThreads
CI / check (pull_request) Failing after 1m28s
Instead of hardcoding workflow as empty string for completed/cancelled
threads, use resolveWorkflowFromHead to get the actual workflow hash
from the CAS chain, consistent with active thread handling.

Closes #46
2026-06-04 15:35:08 +08:00
xiaomo bbea89c067 Merge pull request 'refactor: unified thread storage + resume completed threads' (#45) from refactor/39-unified-thread-storage into main
CI / check (push) Failing after 1m26s
refactor: unified thread storage + resume completed threads (#45)
2026-06-04 07:25:56 +00:00
xingyue bda3e3a861 feat(cli): resume completed threads (衔尾蛇: end → start)
CI / check (pull_request) Failing after 3m45s
uwf thread resume now supports completed threads:
- Evaluates workflow graph from $START to find first role
- Clears completed state (status → idle, completedAt → null)
- Builds resume prompt with supplement context
- Full CAS chain preserved for rich context

Suspended resume behavior unchanged.
Cancelled/idle threads still rejected.

425 tests pass.

Part of #39, closes #43
2026-06-04 15:13:47 +08:00